OrionLLM/GRM-2.6-Air-Opus
Text Generation • 1B • Updated • 373 • 3
DedeProGames PRO
DedeProGames
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
updated a model about 1 hour ago
OrionLLM/GRM-2.6-Air-Opus new activity about 22 hours ago
OrionLLM/GRM-2.6-Plus-0628:Great model! But I have some problems. updated a model about 22 hours ago
OrionLLM/GRM-2.6-Plus-0628Organizations
updated a
model about 1 hour ago
Great model! But I have some problems.
3
#3 opened 1 day ago
by 
NikiKrutan
updated a
model about 22 hours ago
reacted to ProCreations's post with 🤝😔🚀😎🔥🤗➕🤯❤️👀🧠👍 1 day ago
Post
1991
what should i do for 200 followers... hmmmm... top reply to this post (most emojis) wins, just not anything too crazy
- 11 replies
liked a
Space 4 days ago
reacted to Banaxi-Tech's post with 👀🔥 5 days ago
Post
3595
We're excited to announce BananaMind 2V, our small vision model series!
These models are NOT released yet.
We will release them in mid-august!
BananaMind 2V will include:
BananaMind 2V 256M, the flagship based on BananaMind 2 Pro (BananaMind 2 Pro is not released yet).
BananaMind 2V 100M, our mid model, based on BananaMind 2 Medium.
BananaMind 2V 50M, our smallest vision model, based on BananaMind 2 Mini.
These are currently unreleased and will release in mid-august.
Our training will start after BananaMind 2 Pro has finished training.
These models are NOT released yet.
We will release them in mid-august!
BananaMind 2V will include:
BananaMind 2V 256M, the flagship based on BananaMind 2 Pro (BananaMind 2 Pro is not released yet).
BananaMind 2V 100M, our mid model, based on BananaMind 2 Medium.
BananaMind 2V 50M, our smallest vision model, based on BananaMind 2 Mini.
These are currently unreleased and will release in mid-august.
Our training will start after BananaMind 2 Pro has finished training.
liked a
Space 6 days ago
reacted to vineeth98's post with 👍 6 days ago
Post
875
I made a speedrun leaderboard for LoRA fine-tuning. One frozen task (Qwen2.5-1.5B to 57% on GSM8K), one GPU, fastest training run wins. Every record gets re-run 3x with fresh seeds on identical hardware before it counts, so no self-reported numbers.
The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits.
Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone.
vineeth98/lora-speedrun
The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits.
Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone.
vineeth98/lora-speedrun
- 7 replies